Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to the phrase "as" used in various contexts, particularly in comparisons and explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adera
    -0.16
    spor
    -0.15
    aira
    -0.15
    anford
    -0.15
    listed
    -0.14
    hiro
    -0.14
    andin
    -0.14
    aban
    -0.14
    atown
    -0.14
    еж
    -0.14
    POSITIVE LOGITS
    NTAX
    0.17
    908
    0.15
     wholes
    0.15
    io
    0.14
    oda
    0.14
    wert
    0.14
    weis
    0.14
     pointed
    0.14
     Sandwich
    0.14
     far
    0.14
    Act Density 0.055%

    No Known Activations